Learning to Rank at SEA with Harrie Oosterhuis and Rolf Jagerman

***
IMPORTANT: You will be able to view the Zoom link once you 'attend' the meetup on this page.
***

SEA is back again in November! This month's SEA features Harrie Oosterhuis (Radboud University) and Rolf Jagerman (Google) and is all about Learning to Rank.

17.00: Harrie Oosterhuis (Radboud University)

Title: Unifying Online and Counterfactual Learning to Rank

Abstract:
Search and recommendation systems are vital for the accessibility of content on the internet. Search engines allow users to search through large online collections with little effort. Recommendation systems help users discover content that they may not know they find interesting. The basis for these systems are ranking models that turn collections of items into rankings: small ordered lists of items to be displayed to users. Modern ranking models are mostly optimized based on user interactions. Generally, learning from user behavior leads to systems that receive more user engagement than those optimized based on expert judgements. However, user interactions are biased indicators of user preference: often whether something is interacted has less to do with preference and more with where and how it was presented.

In response to this bias problem, recent years have seen the introduction and development of the unbiased Learning to Rank field. State-of-the-art methods in this field are divided into online approaches - that learn by directly interacting with users - and counterfactual approaches - that learn from historical interactions. Existing online methods are hindered without online interventions and thus should not be applied counterfactually. Conversely, counterfactual methods cannot directly benefit from online interventions.

In this talk, we propose a novel intervention-aware estimator for both counterfactual and online Learning to Rank. With the introduction of the intervention-aware estimator, we aim to bridge the online/counterfactual division as it is shown to be highly effective in both online and counterfactual scenarios. The estimator corrects for the effect of position bias, trust bias, and item-selection bias by using corrections based on the behavior of the logging policy and on online interventions: changes to the logging policy made during the gathering of click data. Our experimental results, conducted in a semi-synthetic experimental setup, show that, unlike existing counterfactual methods, the intervention-aware estimator can greatly benefit from online interventions.

17.30: Rolf Jagerman (Google)
Title: Bootstrapping Recommendations at Chrome Web Store.

Google Chrome, one of the world's most popular web browsers, features an extension framework allowing third-party developers to enhance the browser's functionality. Chrome extensions are distributed through the Chrome Web Store (CWS), a Google-operated online marketplace. In this talk I will share practical experiences from building large-scale recommender systems for CWS under various real-world constraints, such as privacy constraints, data sparsity and skewness issues and product design choices. I will focus on how we developed three recommendation systems from scratch: non-personalized recommendations, related recommendations and personalized recommendations.

---
This is (still) an online event. The URL will be shared close to the day of the event. All times are Amsterdam times.

Into numbers? These SEA talks are SEA talks #181 and #182.